NeuROM provides an interpretable deep neural network architecture that uses tensor decomposition to give a parametric reduced-order model.
This release enables the usage of nonlinear ROM on 3D geometries and adds new built-in losses.
4.0.2
**NeuROM** provides an interpretable deep neural network architecture that uses tensor decomposition to give a parametric reduced-order model.
This release enables the usage of **3D geometries**.
4.0.1
3.1.21
3.1.17
Release of the code in its version used for [Finite Element Neural Network Interpolation: Hybridisation with the Proper Generalised Decomposition for surrogate modelling]
3.1.6
Release of the code in its version used for [Finite Element Neural Network Interpolation: Interpretable Neural Networks for solving PDEs]